lora model, need gpu

.gradio/certificate.pem

@@ -0,0 +1,31 @@
+-----BEGIN CERTIFICATE-----
+MIIFazCCA1OgAwIBAgIRAIIQz7DSQONZRGPgu2OCiwAwDQYJKoZIhvcNAQELBQAw
+TzELMAkGA1UEBhMCVVMxKTAnBgNVBAoTIEludGVybmV0IFNlY3VyaXR5IFJlc2Vh
+cmNoIEdyb3VwMRUwEwYDVQQDEwxJU1JHIFJvb3QgWDEwHhcNMTUwNjA0MTEwNDM4
+WhcNMzUwNjA0MTEwNDM4WjBPMQswCQYDVQQGEwJVUzEpMCcGA1UEChMgSW50ZXJu
+ZXQgU2VjdXJpdHkgUmVzZWFyY2ggR3JvdXAxFTATBgNVBAMTDElTUkcgUm9vdCBY
+MTCCAiIwDQYJKoZIhvcNAQEBBQADggIPADCCAgoCggIBAK3oJHP0FDfzm54rVygc
+h77ct984kIxuPOZXoHj3dcKi/vVqbvYATyjb3miGbESTtrFj/RQSa78f0uoxmyF+
+0TM8ukj13Xnfs7j/EvEhmkvBioZxaUpmZmyPfjxwv60pIgbz5MDmgK7iS4+3mX6U
+A5/TR5d8mUgjU+g4rk8Kb4Mu0UlXjIB0ttov0DiNewNwIRt18jA8+o+u3dpjq+sW
+T8KOEUt+zwvo/7V3LvSye0rgTBIlDHCNAymg4VMk7BPZ7hm/ELNKjD+Jo2FR3qyH
+B5T0Y3HsLuJvW5iB4YlcNHlsdu87kGJ55tukmi8mxdAQ4Q7e2RCOFvu396j3x+UC
+B5iPNgiV5+I3lg02dZ77DnKxHZu8A/lJBdiB3QW0KtZB6awBdpUKD9jf1b0SHzUv
+KBds0pjBqAlkd25HN7rOrFleaJ1/ctaJxQZBKT5ZPt0m9STJEadao0xAH0ahmbWn
+OlFuhjuefXKnEgV4We0+UXgVCwOPjdAvBbI+e0ocS3MFEvzG6uBQE3xDk3SzynTn
+jh8BCNAw1FtxNrQHusEwMFxIt4I7mKZ9YIqioymCzLq9gwQbooMDQaHWBfEbwrbw
+qHyGO0aoSCqI3Haadr8faqU9GY/rOPNk3sgrDQoo//fb4hVC1CLQJ13hef4Y53CI
+rU7m2Ys6xt0nUW7/vGT1M0NPAgMBAAGjQjBAMA4GA1UdDwEB/wQEAwIBBjAPBgNV
+HRMBAf8EBTADAQH/MB0GA1UdDgQWBBR5tFnme7bl5AFzgAiIyBpY9umbbjANBgkq
+hkiG9w0BAQsFAAOCAgEAVR9YqbyyqFDQDLHYGmkgJykIrGF1XIpu+ILlaS/V9lZL
+ubhzEFnTIZd+50xx+7LSYK05qAvqFyFWhfFQDlnrzuBZ6brJFe+GnY+EgPbk6ZGQ
+3BebYhtF8GaV0nxvwuo77x/Py9auJ/GpsMiu/X1+mvoiBOv/2X/qkSsisRcOj/KK
+NFtY2PwByVS5uCbMiogziUwthDyC3+6WVwW6LLv3xLfHTjuCvjHIInNzktHCgKQ5
+ORAzI4JMPJ+GslWYHb4phowim57iaztXOoJwTdwJx4nLCgdNbOhdjsnvzqvHu7Ur
+TkXWStAmzOVyyghqpZXjFaH3pO3JLF+l+/+sKAIuvtd7u+Nxe5AW0wdeRlN8NwdC
+jNPElpzVmbUq4JUagEiuTDkHzsxHpFKVK7q4+63SM1N95R1NbdWhscdCb+ZAJzVc
+oyi3B43njTOQ5yOf+1CceWxG1bQVs5ZufpsMljq4Ui0/1lvh+wjChP4kqKOJ2qxq
+4RgqsahDYVvTH9w7jXbyLeiNdd8XM2w9U/t7y0Ff/9yi0GE44Za4rF2LN9d11TPA
+mRGunUHBcnWEvgJBQl9nJEiU0Zsnvgc/ubhPgXRR4Xq37Z0j4r7g1SgEEzwxA57d
+emyPxgcYxn/eR44/KJ4EBs+lVDR3veyJm+kXQ99b21/+jh5Xos1AnX5iItreGCc=
+-----END CERTIFICATE-----

README.md

@@ -7,7 +7,7 @@ sdk: gradio
 sdk_version: 5.6.0
 app_file: app.py
 pinned: false
-python_version: 3.10.0
+python_version: 3.11.0
 ---
 
 Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference

app.py

@@ -51,7 +51,7 @@ def submit_to_model():
                 {
                     "role": "system",
                     "content": (
-                        "You are a world-renowned chef, celebrated for your expertise..."
+                        "You are a world-renowned chef, celebrated for your expertise in creating delectable dishes from diverse cuisines. You have a vast knowledge of ingredients, cooking techniques, and dietary preferences. Your role is to suggest personalized recipes based on the ingredients available, dietary restrictions, or specific meal requests. Please provide clear, step-by-step instructions and any useful tips to enhance the dish's flavor or presentation. Begin by introducing the recipe and why it’s a great choice."
                     ),
                 },
                 {"role": "user", "content": prompt},

peft_app.py → lora.py

@@ -1,19 +1,17 @@
 import gradio as gr
 
-from transformers import TextStreamer
+from transformers import TextStreamer, TextIteratorStreamer
+
+from threading import Thread
 
 from unsloth import FastLanguageModel
 
-max_seq_length = 2048
-dtype = None
 load_in_4bit = True
 
 peft_model_id = "ID2223JR/lora_model"
 
 model, tokenizer = FastLanguageModel.from_pretrained(
     model_name=peft_model_id,
-    max_seq_length=max_seq_length,
-    dtype=dtype,
     load_in_4bit=load_in_4bit,
 )
 FastLanguageModel.for_inference(model)
@@ -50,6 +48,7 @@ def submit_to_model():
     prompt = f"Using the following ingredients, suggest a recipe:\n\n" + "\n".join(
         ingredients_list
     )
+    ingredients_list.clear()
 
     messages = [
         {
@@ -64,16 +63,19 @@ def submit_to_model():
         add_generation_prompt=True,  # Must add for generation
         return_tensors="pt",
     )
-    text_streamer = TextStreamer(tokenizer, skip_prompt=True)
-
-    return model.generate(
-        input_ids=inputs,
-        streamer=text_streamer,
-        max_new_tokens=128,
-        use_cache=True,
-        temperature=1.5,
-        min_p=0.1,
-    )
+
+    text_streamer = TextIteratorStreamer(tokenizer, skip_prompt=True)
+
+    generation_kwargs = dict(inputs=inputs, streamer=text_streamer, use_cache=True, temperature=0.3, min_p=0.1)
+    thread = Thread(target=model.generate, kwargs=generation_kwargs)
+    thread.start()
+
+
+    content = ""
+    for text in text_streamer:
+        print(text)
+        content += text
+        yield content
 
 
 # App